Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to scams and fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    financial crime and scams

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of scams, fraud, impersonation, and related deceptive or criminal activities.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     capucha
    -0.38
     נוס
    -0.35
     صوتيه
    -0.34
    umbersome
    -0.34
    PreInfinity
    -0.33
    ängerin
    -0.32
     müm
    -0.32
     costas
    -0.32
     nevoie
    -0.31
     Lohan
    -0.31
    POSITIVE LOGITS
     Italijani
    0.53
     resourceCulture
    0.50
    EndContext
    0.49
    BufferException
    0.49
     Alert
    0.45
    fitrión
    0.45
     Италијани
    0.45
    featureID
    0.45
    참고
    0.45
    tigkeits
    0.43
    Act Density 0.005%

    No Known Activations